Integration of Neonatal Mortality Prediction Models into a Clinical Decision Support System

Martirosyan, Hasmik

doi:10.22215/etd/2015-10644

Cited by 2 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce bias, a 5by2 cross validation technique was applied at all stages (Dietterich, 1998). This work also made use of the ANN Builder tool developed by H. Martirosyan, in place of the previous ANN tool, MIRG ANN (Martirosyan, 2014;Rybchynski, 2005). Then a comparative analysis is done of the BORN data results, with the results from PRAMS analysis preformed by Nicole Yu, (Yu, 2009).…”

Section: Thesis Objectivesmentioning

confidence: 99%

“…Further, a usability case study was performed by Martirosyan, which involved parents who had a neonate who did not graduate (did not survive) from the NICU. The two parents who participated provided feedback with suggestions for improvement, which were encouraging, regarding the usefulness of the PPADs tool (Martirosyan, 2014). MIRG is developing a similar support system for perinatal care scenarios, Physicians -Mother Decision Support (PMODS).…”

Section: Physician -Parent Decision Support (Ppads)mentioning

confidence: 99%

“…Despite having various features and functionalities added by MIRG students to the basic MATLAB tool, the manual steps involved in the risk estimation by the MIRG ANN RFW posed difficulties for the integration of ANN models into the systems and models that require real-time analysis (Martirosyan, 2014). As well, the RFW and the prediction tool developed in MATLAB, requires a commercial license to use.…”

Section: Mirg Annmentioning

confidence: 99%

“…Martirosyan's thesis work explored several open sources libraries to create ANN models, and make predictions in a real time environment. Martirosyan found the Fast Artificial Neural Network (FANN) library to be suitable to MIRG's work for the following reasons (Martirosyan, 2014):…”

Section: Fann Library (Ann Builder)mentioning

confidence: 99%

“…As mentioned previously, the 5-by-2 cross validation method was used to obtain more reliable risk estimation models. Martirosyan (2014) adapted and modified scripts created by Gilchrist (2012) to achieve a division into train, test and verification sets for ANNs. The process was as follows as outlined by Martirosyan (2014): 1.…”

Section: By2 Cross-validation and Preparation Filesmentioning

confidence: 99%

See 4 more Smart Citations

An Integrated Machine Learning Approach to Optimize the Estimation of Preterm Birth

Ong¹

View full text Add to dashboard Cite

This thesis describes a new methodology used in conjunction with artificial intelligence tools to create multiple models for prediction of preterm birth in obstetrical environments. The data mining approach integrates: Decision Trees (DTs), Artificial Neural Networks (ANNs) -specifically a Feed Forward Back Propagation ANN, and Case Based Reasoning System (CBRS).This work also introduces a 5by2 cross validation method, assesses two methods of attribute selection, and considers data prevalence (15% and 8.1%) in training and testing networks. Two databases were assessed from two countries: BORN (Canada) and PRAMS (USA). Best BORN results used selection method 2, had sensitivities of 50.53%, 53.96%, specificities of 91.61%, 95.40%, and area under curves (AUC) of 0.7721, 0.7970 for Parous and Nulliparous cases respectively. Best PRAMS results used selection method 1, had sensitivities of 68.15%, 40.35%, specificities of 64.71%, 94.57%, and area under curves (AUC) of 0.8452, 0.7064 for Parous and Nulliparous cases respectively. iii Above all, challenge yourself. You may well surprise yourself at what strengths you have, what you can accomplish. -Cecile Springer iv AcknowledgementsFirst and foremost, I would like to take this opportunity to thank my thesis supervisor, Dr. Monique Frize, for her support, encouragement and guidance. I am very grateful to have had the opportunity to work with you.

show abstract

Section: Thesis Objectivesmentioning

confidence: 99%

Section: Physician -Parent Decision Support (Ppads)mentioning

confidence: 99%

Section: Mirg Annmentioning

confidence: 99%

Section: Fann Library (Ann Builder)mentioning

confidence: 99%

Section: By2 Cross-validation and Preparation Filesmentioning

confidence: 99%

See 3 more Smart Citations